Google Chrome has incorporated speech-to-text functionality since its version 25. However, it is only now that we have robust tools and APIs to integrate artificial intelligence, intention recognition, and LLM (Language Model) services, opening up new possibilities for the development of intelligent services, both within the browser and across other communication channels.

In this lecture, we will embark on a practical journey that spans from utilizing the speech-to-text and text-to-speech (TTS) functionalities in the browser to integrating these capabilities into cloud platforms, providing a broader and more in-depth experience.